Colour Features Extraction Techniques and Approaches for Content-Based Image Retrieval (CBIR) System  

作　　者：Muhammad Naim Abdullah Mohd Afizi Mohd Shukran Mohd Rizal Mohd Isa Nor Suraya Mariam Ahmad Mohammad Adib Khairuddin Mohd Sidek Fadhil Mohd Yunus Fatimah Ahmad Muhammad Naim Abdullah;Mohd Afizi Mohd Shukran;Mohd Rizal Mohd Isa;Nor Suraya Mariam Ahmad;Mohammad Adib Khairuddin;Mohd Sidek Fadhil Mohd Yunus;Fatimah Ahmad(Universiti Pertahanan Nasional Malaysia (UPNM), Kuala Lumpur, Malaysia;University Malaysia of Computer Science and Engineering (UNIMY), Selangor, Malaysia;Universiti Pendidikan Sultan Idris (UPSI), Perak, Malaysia)

机构地区：[1]Universiti Pertahanan Nasional Malaysia (UPNM), Kuala Lumpur, Malaysia [2]University Malaysia of Computer Science and Engineering (UNIMY), Selangor, Malaysia [3]Universiti Pendidikan Sultan Idris (UPSI), Perak, Malaysia

出　　处：《Journal of Materials Science and Chemical Engineering》2021年第7期29-34,共6页材料科学与化学工程（英文）

摘　　要：<div style="text-align:justify;"> An image retrieval system was developed purposely to provide an efficient tool for a set of images from a collection of images in the large database that matches the user’s requirements in similarity evaluations such as image content similarity, edge, and colour similarity. Retrieving images based on the contents which are colour, texture, and shape is called content-based image retrieval (CBIR). This paper discusses and describes about the colour features technique for image retrieval systems. Several colour features technique and algorithms produced by the previous researcher are used to calculate the similarity between extracted features. This paper also describes about the specific technique about the colour basis features and combined features (hybrid techniques) between colour and shape features. </div><div style="text-align:justify;"> An image retrieval system was developed purposely to provide an efficient tool for a set of images from a collection of images in the large database that matches the user’s requirements in similarity evaluations such as image content similarity, edge, and colour similarity. Retrieving images based on the contents which are colour, texture, and shape is called content-based image retrieval (CBIR). This paper discusses and describes about the colour features technique for image retrieval systems. Several colour features technique and algorithms produced by the previous researcher are used to calculate the similarity between extracted features. This paper also describes about the specific technique about the colour basis features and combined features (hybrid techniques) between colour and shape features. </div>

关 键 词：Content-Based Image Retrieval Colour Features CBIR 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]